© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 14752
    Prev
    Next
    INDEX
    Explanations

    references to international agreements and legal principles, particularly related to human rights and regulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Juliushanhanhan/llama-3-8b-it-res/blocks.25.hook_resid_post
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    gated
    Context Size
    1,024
    Dataset
    Juliushanhanhan/openwebtext-1b-llama3-tokenized-cxt-1024
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ness
    -0.24
    NESS
    -0.17
    loo
    -0.15
    شاÙĩ
    -0.15
    ç©´
    -0.15
    .CreateInstance
    -0.15
    Ñĭ
    -0.15
    gesch
    -0.15
    еÑģÑı
    -0.15
    .Selenium
    -0.15
    POSITIVE LOGITS
    alogy
    0.38
    alog
    0.33
    ious
    0.20
    usk
    0.17
    ontology
    0.16
    /pro
    0.16
    iac
    0.16
     expression
    0.16
    -expression
    0.16
    ultimate
    0.15
    Activations Density 0.006%

    No Known Activations